halixness/understanding-CLIP

Repo from the "Learning with limited labeled data" seminar @ Uni of Tuebingen. A collection of notes, notebooks and slideshows to understand CLIP and Natural language supervision.

29
/ 100
Experimental

This project provides resources to help you understand CLIP and how it uses natural language to interpret images. It explains how you can input images and text descriptions to link them, or even generate text from images, helping you build systems that understand visual content without extensive manual labeling. This is for researchers and practitioners exploring advanced computer vision, especially those interested in connecting images with descriptive language.

No commits in the last 6 months.

Use this if you need to grasp how models can learn to recognize visual content using natural language descriptions, enabling zero-shot recognition or image-text linking.

Not ideal if you're looking for a plug-and-play solution for a specific image analysis task rather than a deep dive into the underlying research and concepts.

computer-vision-research image-text-retrieval zero-shot-learning multimodal-AI natural-language-supervision
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 15 / 25

How are scores calculated?

Stars

17

Forks

4

Language

Jupyter Notebook

License

Last pushed

Apr 13, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/halixness/understanding-CLIP"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.